System and method for object and obstacle detection and classification in collision avoidance of railway applications

Abstract

A system for detection and identification of objects and obstacles near, between or on railway comprise several forward-looking imagers adapted to cover each different range forward and preferably to be sensitive each to different wavelength of radiation, including visible light, LWIR, and SWIR. The substantially homogeneous temperature along the rail the image of which is included in an imager frame assists in identifying and distinguishing the rail from the background Image processing is applied to define living creature in the image frame and to distinguish from a man-made object based on temperature of the body. Electro optic sensors (e.g. thermal infrared imaging sensor and visible band imaging sensor) are used to survey and monitor railway scenes in real time.

The invention claimed is: 
     
       1. A system for rail obstacle detection and avoidance, the system comprising:
 an imager configured to be aimed to a direction of a travel along a rail; and 
 a controller configured to:
 receive a plurality of images from the imager; 
 based on the received images:
 perform image-based rail mapping; 
 perform object detection and object classification; 
 
 based on the image-based rail mapping, the object detection and the object classification, determine whether or not the received images comprise an object posing threat or being potential obstacle in a vicinity of the rail; 
 perform the object classification by analyzing a silhouette of an object, the silhouette being a shape of an outer boundary of the object in the received images; and 
 analyze the silhouette of the object by:
 decomposing the silhouette into adjoining partitions, 
 classifying the object based on the adjoining partitions of the silhouette. 
 
 
 
     
     
       2. The system of  claim 1 , wherein the controller is configured to provide an alarm signal when the object posing threat or being potential obstacle in the vicinity of the rail is detected. 
     
     
       3. The system of  claim 1 , wherein the controller is configured to perform the image-based rail mapping by:
 spatially detecting the rail in the received images, and 
 tracking the detected rail over time as the rail shifts in location and orientation. 
 
     
     
       4. The system of  claim 1 , wherein the controller is configured to perform the object detection by:
 spatially detecting an object in the received images; and 
 tracking the detected object over time as the object shifts in location. 
 
     
     
       5. The system of  claim 1 , further comprising at least two imagers operative in different wavelength ranges with respect to each other. 
     
     
       6. A system for rail obstacle detection and avoidance, the system comprising:
 an imager configured to be aimed to a direction of a travel of a train along a rail; 
 a geographical location module; and 
 a controller configured to:
 receive a plurality of images from the imager; 
 based on the received images, perform object detection and object classification; 
 based on a geo-based rail map, information from the geographical location module and the object detection and the object classification, determine whether or not the received images comprise an object posing threat or being potential obstacle in a vicinity of the rail; 
 perform the object classification by analyzing a silhouette of an object; and 
 analyze the silhouette of the object by:
 decomposing the silhouette into adjoining partitions, 
 classifying the object based on the adjoining partitions of the silhouette. 
 
 
 
     
     
       7. The system of  claim 6 , wherein the controller is configured to provide an alarm signal when the object posing threat or being potential obstacle in the vicinity of the rail is detected. 
     
     
       8. The system of  claim 6 , wherein the controller is configured to, based on the received images, perform image-based rail mapping so as to generate an image-based rail map. 
     
     
       9. The system of  claim 8 , wherein the controller is configured to, based on the information from the geographical location module, augment the image-based rail map with the geo-based rail map. 
     
     
       10. The system of  claim 6 , wherein the controller is configured to, based on the received images, generate a three-dimensional (3D) model of an area in a vicinity of the rail. 
     
     
       11. The system of  claim 10 , wherein the controller is configured to, based on the information from the geographical location module, augment the 3D model with the geo-based rail map. 
     
     
       12. The system of  claim 8 , wherein the controller is configured to perform the image-based rail mapping by:
 spatially detecting the rail in the received images, and 
 tracking the detected rail over time as the rail shifts in location and orientation. 
 
     
     
       13. The system of  claim 6 , further comprising at least two imagers operative in different wavelength ranges with respect to each other.